| 講演抄録/キーワード |
| 講演名 |
2011-07-23 09:30
Nonlinear Normalization Using q-Logarithm for Robust Speech Recognition ○Hilman F. Pardede・Koichi Shinoda(Tokyo Inst. of Tech.)・Koji Iwano(Tokyo City Univ.) SP2011-49 |
| 抄録 |
(和) |
(まだ登録されていません) |
| (英) |
The performance of speech recognition degrades signicantly in the noisy environment. Most compensation methods to improve the robustness of speech recognition assume uncorrelated speech, additive and convolutive noise. However, the nonlinear nature of speech and noise signals may cause noise and speech to b e correlated. To deal with this problem, we propose compensation in an intermediate domain using q -logarithmic function. The q -logarithmic function is a generalization of the natural logarithmic function and recently used to generalize Shan-non entropy. The q -logarithmic function enables us to transform the spectral from linear to log spectral by varying the q -value. In this paper, we implement spectral mean normalization (LSMN) using q -logarithmic function and call it Generalized-log spectral mean normalization (GLSMN). Our experiments on the Aurora-2 database show that GLSMN improve speech recognition accuracies by 20% compared to cepstral mean normalization (CMN) in mel-frequency domain |
| キーワード |
(和) |
/ / / / / / / |
| (英) |
robust speech recognition / q-logarithmic function / generalized-log spectral mean normalization / / / / / |
| 文献情報 |
信学技報, vol. 111, no. 153, SP2011-49, pp. 45-50, 2011年7月. |
| 資料番号 |
SP2011-49 |
| 発行日 |
2011-07-14 (SP) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
SP2011-49 |